JP7467780B2 - Image processing method, apparatus, device and medium - Google Patents

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to a Chinese patent application bearing application number 202110180571.8 and entitled "Image Processing Method, Apparatus, Device and Medium" filed with the State Intellectual Property Office of China on February 9, 2021, the entire contents of which are incorporated herein by reference.
[Technical field]
The present disclosure relates to the field of multimedia technology, and in particular to an image processing method, apparatus, device, medium, and program product.

With the rapid development of computer technology and mobile communication technology, various video platforms based on electronic devices have been widely used, greatly enriching people's daily lives. More and more users are willing to share their own video works on video platforms for other users to watch.

When creating a video, a user must first perform a series of complex material editing operations on the material, then perform video clip operations on the edited material, and finally generate a video work. If a user is not good at editing materials, not only will the time cost of video creation be high, but the quality of the video work cannot be guaranteed, resulting in a poor user experience.

To solve the above-mentioned technical problem, or to at least partially solve the above-mentioned technical problem, the present disclosure provides an image processing method, an apparatus, a device, a medium, and a computer program product.

According to a first aspect, the present disclosure provides an image processing method, comprising:
identifying a motion state of a first recognition object in an initial video image;
Identifying a motion state of a material object based on a motion state of a first recognition object;
if the motion state of the material object belongs to a first state, synthesizing the material object with the first style video image according to the motion state of the material object to obtain a first target video image;
if the motion state of the material object belongs to a second state, synthesizing the material object with the second style video image according to the motion state of the material object to obtain a second target video image;
The method provides for the first style video image and the second style video image to be different stylized images derived based on an initial video image.

According to a second aspect, the present disclosure provides an image processing device,
a first processing unit arranged to identify a motion state of a first recognition object in an initial video image;
a second processing unit arranged to determine a motion state of the material object based on the motion state of the first recognition object;
a first synthesis unit, configured to synthesize the material object and the first style video image according to the motion state of the material object to obtain a first target video image when the motion state of the material object belongs to a first state;
a second synthesis unit, configured to synthesize the material object and the second style video image according to the motion state of the material object to obtain a second target video image when the motion state of the material object belongs to a second state;
The apparatus provides a first style video image and a second style video image, which are different stylized images derived based on an initial video image.

According to a third aspect, the present disclosure provides an image processing device, comprising:
A processor;
a memory for storing executable instructions;
Including,
The processor provides an image processing device that is adapted to read and execute executable instructions from the memory so as to implement the image processing method according to the first aspect.

According to a fourth aspect, the present disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to realize the image processing method described in the first aspect.

According to a fifth aspect, the present disclosure provides a computer program product including instructions that, when executed on a device, cause the device to perform the image processing method described in the first aspect above.

Compared with the prior art, the technical solutions provided by the embodiments of the present disclosure have the following advantages:
The image processing method, apparatus, device, and medium of the embodiments of the present disclosure identify a motion state of a first recognition object in an initial video image, identify a motion state of a material object based on the motion state of the first recognition object, and determine the motion state of the material object. If the motion state of the material object belongs to the first state, the material object and a first style video image are combined according to the motion state of the material object to obtain a first target video image. If the motion state of the material object belongs to the second state, the material object and a second style video image are combined according to the motion state of the material object to obtain a second target video image. Therefore, material editing can be automatically performed on the initial video image as a video material to obtain an edited composite image, and the user does not need to manually perform material editing. This can reduce the time cost of video production, improve the quality of video works, and improve the user experience.

The above and other features, advantages, and aspects of each embodiment of the present disclosure will become more apparent by reference to the following specific embodiments in conjunction with the accompanying drawings, in which the same or similar reference numerals refer to the same or similar elements throughout the drawings, where the drawings are schematic and parts and elements are not necessarily drawn to scale.
1 is a schematic flow chart of an image processing method according to an embodiment of the present disclosure. 1 is a schematic flow chart of another image processing method according to an embodiment of the present disclosure. 13 is a schematic flow chart of yet another image processing method according to an embodiment of the present disclosure. 1 is a schematic flow chart of an image processing process according to an embodiment of the present disclosure. 1 is a schematic diagram illustrating a configuration of an image processing device according to an embodiment of the present disclosure. FIG. 1 is a schematic diagram of an image processing device according to an embodiment of the present disclosure.

Hereinafter, the embodiments of the present disclosure will be described in more detail with reference to the drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be realized in various forms and should not be construed as being limited to the embodiments described herein, but rather, these embodiments are provided for a deeper and more complete understanding of the present disclosure. It should also be understood that the drawings and embodiments of the present disclosure are used for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

It should be understood that the steps described in the method embodiments of the present disclosure may be performed in different orders and/or in parallel. Also, method embodiments may include additional steps and/or omit the performance of steps that are illustrated. The scope of the present disclosure is not limited in this respect.

As used herein, the term "including" and variations thereof mean an open-ended inclusion, i.e., "including but not limited to." The term "based on" means "based at least in part on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one alternative embodiment," and the term "some embodiments" means "at least some embodiments." Relevant definitions of other terms are provided below.

Note that concepts such as "first" and "second" referred to in this disclosure are used only to distinguish different devices, modules, or units, and are not intended to limit the order or interdependence of functions performed by these devices, modules, or units.

Note that the modifications "one" and "multiple" referred to in this disclosure are illustrative rather than limiting, and should be understood as "one or multiple" unless otherwise indicated herein, as would be understood by one of ordinary skill in the art.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are not intended to limit the scope of these messages or information, but are for illustrative purposes only.

Currently, when creating a video, users must first perform a series of complex material editing operations on the material, then perform video clip operations on the edited material, and finally generate a video work. If users are not good at editing materials, not only will the time cost of video creation be high, but the quality of the video work cannot be guaranteed, resulting in a poor user experience.

To solve the above problems, the embodiments of the present disclosure provide an image processing method, apparatus, device, and medium that can automatically perform material editing on video material.

Below, we will first explain the image processing method according to an embodiment of the present disclosure with reference to Figure 1.

In some embodiments of the present disclosure, the image processing method may be performed by an electronic device. The electronic device may include a device having a communication function, such as a mobile phone, a tablet, a desktop computer, a laptop, an in-vehicle terminal, a wearable electronic device, a multifunction printer, or a smart home device, or may be a device simulated by a virtual machine or a simulator.

Figure 1 shows a schematic flowchart of an image processing method according to an embodiment of the present disclosure.

As shown in FIG. 1, the image processing method includes steps S110 to S140.

Step S110: Identify the motion state of the first recognition object in the initial video image.

In an embodiment of the present disclosure, after acquiring an initial video image, the electronic device can perform motion analysis on a first recognition object in the initial video image based on an object detection method to identify a motion state of the first recognition object.

In some embodiments, the initial video image may be a video image from a video that has already been captured. For example, the initial video image may be a video image from a video stored locally on the electronic device, a video transmitted from another electronic device, a video on the Internet, etc.

In some other embodiments, the initial video image may be a video image captured in real time by an electronic device.

Optionally, in an embodiment of the present disclosure, when the initial video image is a video image captured in real time by an electronic device, the virtual world and the real world can be combined on the screen based on Augmented Reality (AR) technology to realize material editing of the video material, thereby achieving the effect of interacting with the user.

In the embodiment of the present disclosure, the first recognition object may be preset according to actual needs and is not limited here.

In some embodiments, the first recognition object may include any of a person, an animal, or an object.

For example, if the first recognition object is a person, the movement state of the first recognition object can refer to the overall movement state of the person.

In some other embodiments, the first recognition object may include any body part.

For example, if the first recognition object is a hand, the movement state of the first recognition object can refer to the movement state of the hand.

In the embodiment of the present disclosure, the motion type to which the motion state of the first recognition object belongs may be preset according to actual needs and is not limited here.

Optionally, the motion state of the first recognition object may include any one of a movement state of the first recognition object along a target movement direction, a posture change state of the first recognition object to a target object posture, and a rotation state of the first recognition object along a target rotation direction.

In some embodiments, the target movement direction may be preset according to actual needs and is not limited here. For example, the target movement direction may be a depth direction of any angle in the video image. For further example, the target movement direction may be a direction of any angle in the video image plane.

In these examples, the movement state along the target movement direction may include the movement distance along the target movement direction.

When the target object is a hand and the target movement direction is a depth direction perpendicular to the video image, the movement state of the first recognition object may be the movement distance of the hand along the depth direction perpendicular to the video image.

In some other embodiments, the target object pose may be preset according to actual needs, and is not limited here.

In these embodiments, the pose change state for the target object pose may include an amount of pose change for the target object pose.

When the target object is a hand and the target object posture is an open palm posture, the movement state of the first recognition object may be the posture change amount of the hand posture toward the open palm posture.

Furthermore, in some embodiments, the target rotation direction may be preset according to actual needs and is not limited here.

For example, the target rotation direction may be a clockwise or counterclockwise direction at any angle in the depth direction of the video image. For further example, the target direction may be a clockwise or counterclockwise direction in the plane of the video image.

In these embodiments, the rotational state along the target rotation direction may include a rotation angle along the target rotation direction.

When the target object is a hand and the target rotation direction is a clockwise direction in the video image plane, the motion state of the first recognition object may be the rotation angle that the hand rotates in the video image plane.

Step S120: Identify the movement state of the material object based on the movement state of the first recognition object.

In an embodiment of the present disclosure, the electronic device can determine the motion state of the material object in the motion state of the first recognition object after determining the motion state of the first recognition object.

In an embodiment of the present disclosure, the movement state of the material object may be a change state of the positional relationship of the material object with respect to the second recognition object.

The movement state of the material object may be preset according to actual needs and is not limited here. For example, the movement state of the material object may include at least one of an included angle change state with respect to the second recognition object in the target tilt direction, a layer change state with respect to the second recognition object, and a position change state with respect to the second recognition object in the image plane.

The second recognition object may be preset according to actual needs and is not limited here. For example, the second recognition object may be an image body such as a person or an animal.

In some embodiments, the target tilt direction may be preset according to actual needs and is not limited here. For example, the target tilt direction may be a depth direction of any angle in the video image. For further example, the target tilt direction may be a direction of any angle in the video image plane.

In these embodiments, the included angle state with respect to the second recognition object in the target tilt direction may include the included angle with respect to the second recognition object in the target tilt direction.

In some other embodiments, the layer state for the second recognition object may include a layer position for the second recognition object.

For example, the layer position for the second recognition object may include the foreground or background of the second recognition object.

Furthermore, in some embodiments, the positional state in the image plane for the second recognition object may include a relative distance in the image plane for the second recognition object.

In the embodiment of the present disclosure, the material objects may be preset according to actual needs and are not limited here.

For example, the material object may be a scene decoration special effect. For further example, the material object may be a greeting card decoration special effect.

In some embodiments, the material object may include a moving material object. In this case, the motion state of the material object may be the motion state of the moving material object.

For example, the animated material object may include a movable greeting card frame special effect.

For example, if the moving material object is a greeting card frame special effect and the second recognition object is a person, the movement state of the material object is the included angle between the person and the greeting card frame special effect as the greeting card frame special effect tilts in the depth direction perpendicular to the video image. With the movement of the first recognition object, the included angle between the greeting card frame special effect and the person also changes, and the effect of the greeting card frame special effect falling and rising can be realized.

For example, if the moving material object is a greeting card frame special effect and the second recognition object is a person, the movement state of the material object is a layer position relative to the second recognition object, and as the first recognition object moves, the frame special effect may switch from the foreground of the person to the background of the person, or from the background of the person to the foreground of the person.

In some other embodiments, to further enhance the aesthetics of the edited video material, the material objects may include moving material objects and fixed material objects. In this case, the motion state of the material objects may be the motion state of the moving material objects. Fixed material objects are displayed in a fixed, pre-set display state and do not have a motion state.

For example, the moving material object may include a movable greeting card frame feature, and the fixed material object may include a non-movable greeting card bottom frame special effect.

In an embodiment of the present disclosure, after identifying the motion state of the material object, the electronic device can further determine the motion state of the material object, and if the motion state of the material object belongs to a first state, executes step S130, and if the motion state of the material object belongs to a second state, executes step S140.

Step S130: if the motion state of the material object belongs to the first state, the material object and the first style video image are combined according to the motion state of the material object to obtain a first target video image.

In an embodiment of the present disclosure, the first state may represent a first positional relationship between the material object and a second recognition object in the initial video image.

When the movement state of the material object is a state in which an included angle exists between the material object and the second recognition object in the target tilt direction, the first positional relationship may specifically be a relationship in which the angle change value of the included angle falls within a first angle range, or the first relationship may specifically be a relationship in which the angles of the included angles all fall within a first angle range during the change.

For example, if the target tilt direction is the depth direction perpendicular to the video image, the first positional relationship may be specifically a relationship in which the included angle is within an angle range of [0°, 45°] in the depth direction perpendicular to the video image.

When the motion state of the material object is a layer position relative to the second recognition object, the first positional relationship may specifically be a relationship in which the material object is located in the foreground of the second recognition object.

When the movement state of the material object is a state in which there is a distance from the second recognition object in the image plane, the first positional relationship may specifically be a relationship in which the change value of the relative distance falls within a first distance range, or a relationship in which all of the relative distances fall within the first distance range during the change.

Therefore, when the electronic device determines that the motion state of the material object belongs to the first state, it obtains a first style video image corresponding to the initial video image, and further combines the material object with the first style video image according to the motion state of the material object to obtain a first target video image corresponding to the first state.

In an embodiment of the present disclosure, the first style video image may be a video image having a first style obtained based on an initial video image, the first style being a style corresponding to a first state.

Step S140: If the motion state of the material object belongs to the second state, the material object and the second style video image are combined according to the motion state of the material object to obtain a second target video image.

In an embodiment of the present disclosure, the second state can represent a second positional relationship between the material object and a second recognition object in the initial video image.

When the movement state of the material object is a state in which an included angle exists between the material object and the second recognition object in the target tilt direction, the second positional relationship may specifically be a relationship in which the angle change value of the included angle falls within a second angle range, or the second relationship may specifically be a relationship in which the angles of the included angles all fall within the second angle range during the change.

For example, if the target tilt direction is a depth direction perpendicular to the video image, the second positional relationship may be specifically a relationship in which the included angle falls within an angle range of [45, 90] in the depth direction perpendicular to the video image.

When the movement state of the material object is a layer position relative to the second recognition object, the second positional relationship may specifically be a relationship in which the material object is located in the background of the second recognition object.

When the movement state of the material object is a state in which there is a distance from the second recognition object in the image plane, the second positional relationship may specifically be a relationship in which the change value of the relative distance falls within the second distance range, or a relationship in which all of the relative distances fall within the second distance range during the change.

Therefore, when the electronic device determines that the motion state of the material object belongs to the second state, it can obtain a second style video image corresponding to the initial video image, and further combine the material object with the second style video image according to the motion state of the material object to obtain a second target video image corresponding to the second state.

In an embodiment of the present disclosure, the second style video image may be a video image having a second style obtained based on the initial video image, the second style being a style corresponding to a second state.

Furthermore, the first style video image and the second style video image are different stylized images obtained based on the initial video image, i.e., the first style is different from the second style.

In an embodiment of the present disclosure, the motion state of a first recognition object is identified in an initial video image, the motion state of a material object is identified based on the motion state of the first recognition object, and the motion state of the material object is determined. If the motion state of the material object belongs to the first state, the material object and the first style video image are combined according to the motion state of the material object to obtain a first target video image. If the motion state of the material object belongs to the second state, the material object and the second style video image are combined according to the motion state of the material object to obtain a second target video image. Therefore, material editing can be automatically performed on the initial video image as a video material to obtain an edited composite image, and the user does not need to manually perform material editing. This can reduce the time cost of video creation, improve the quality of the video work, and improve the user's experience.

In the embodiment of the present disclosure, in order to accurately identify the motion state of the first recognition object, step S110 may specifically include steps S111 to S112.
Step S111: detecting a display parameter variable of a first recognition object in an initial video image.

If the initial video image is the video image of the first frame, it can be determined that the display parameter variable of the first recognition object is zero.

If the initial video image is a non-first frame video image, a previous reference video image adjacent to the initial video image can be obtained.

In this case, the electronic device can detect a first display parameter in an initial video image of a first recognition object and a second display parameter in a reference video image based on an object detection method, and then subtract the second display parameter from the first display parameter to obtain a display parameter variable of the first recognition object.

The parameter types of the first display parameter and the second display parameter may be parameter types for calculating the movement state of the first recognition object that are preset according to actual needs, and are not limited here.

Optionally, the display parameters may include at least one of an object pose of the first recognition object, a display size of the first recognition object, a display position of the first recognition object in the video image, and a distance of the first recognition object relative to a third recognition object.

The third recognition object may be a pre-selected position reference object according to actual needs, and is not limited here. For example, if the first recognition object is a hand, the third recognition object may be a head.

For example, assuming that the motion state of the first recognition object is the distance the hand moves along the depth direction perpendicular to the video image, the display parameter may be the display size of the hand, the first display parameter may be the first display size of the hand in the initial video image, and the second display parameter may be the second display size of the hand in the reference video image, and the second display size is subtracted from the first display size to obtain the display parameter variable of the first recognition object.

Step S112: Identify the movement state of the first recognition object based on the display parameter variable.

In an embodiment of the present disclosure, the electronic device may set the display parameter variable as the motion state of the first recognition object.

For example, if the movement state of the first recognition object is the distance the hand moves along the depth direction perpendicular to the video image, the first display parameter is the first display size of the hand in the initial video image, and the second display parameter is the second display size of the hand in the reference video image, when the display parameter variable is greater than or equal to zero, the display parameter variable can be the distance the hand moves toward the depth direction perpendicular to the video image, and when the display parameter variable is zero dissatisfaction, the display parameter variable can be the distance the hand moves away from the depth direction perpendicular to the video image.

As a result, in an embodiment of the present disclosure, by detecting display parameter variables in an initial video image of the first recognition object, it is possible to reliably analyze the movement of the first recognition object and further identify the movement state of the first recognition object.

In another embodiment of the present disclosure, the method of acquiring style video images corresponding to different motion states of material objects is different.

In some embodiments of the present disclosure, the first style video image may be an image in which an initial video image has been subjected to style transition processing.

Furthermore, before step S130, the image processing method further comprises:
performing a face stylization process on the initial video image to obtain a stylized face image;
performing a non-face stylization process on the initial video image to obtain a stylized non-face image;
Including,
The stylized facial image and the stylized non-facial image are composited into a first style video image.

First, the electronic device can perform face detection on an initial video image to obtain a face region image in the initial video image, and input the face region image into a pre-trained face stylization model to obtain a stylized face image.

For example, the face stylization model may be a cartoon face transformation model, and the electronic device may input a face region image into the cartoon face transformation model to obtain a cartoon-style stylized face image.

The electronic device can then use a pre-configured background stylization algorithm to perform a non-face stylization process on the non-face regions of the initial video image to obtain a stylized non-face image.

For example, the background stylization algorithm may be an occult background transformation algorithm, and the electronic device may use the occult background transformation algorithm to perform a non-face stylization process on the non-face regions of the initial video image to obtain a cartoon-style stylized non-face image.

Finally, the electronic device can determine the relative position of the face region image in the initial video image and stitch the stylized face image to the relative position of the stylized non-face image to obtain a first styled video image.

In these embodiments, optionally, in step S130, synthesizing the material object with the first style video image according to the motion state of the material object to obtain a first target video image is specifically performed by:
The method may include the step of superimposing the material object on the first style video image in a state in which the material object is in motion to obtain a first target video image.

If the material object includes a moving material object, the moving material object is directly superimposed on the specified position of the first style video image in the motion state of the moving material object to obtain a first target video image.

When the material objects include moving material objects and fixed material objects, the moving material objects are directly superimposed at the specified position of the first style video image in the motion state of the moving material objects, and the fixed material objects are superimposed on the first style video image in a preset display state to obtain a first target video image.

In some other embodiments of the present disclosure, the second style video image may be the initial video image.

Further, before step S140, the image processing method may further include a step of setting the initial video image as a second style video image.

Specifically, the electronic device can directly render the initial video image into a second style video image, so that the second style video image is the initial video image having the original image style.

As a result, in the embodiment of the present disclosure, different stylization processing methods can be used to obtain style video images of different styles corresponding to the initial video image, further enhancing the interest of interaction.

In these embodiments, optionally, in step S140, synthesizing the material object with the second style video image according to the motion state of the material object to obtain a second target video image is specifically:
The method may include a step of first performing image segmentation on the second style video image to obtain a second recognition object image in the second style video image and a background image other than the second recognition object image, and then superimposing the material object on the second recognition object image and the background image in a motion state of the material object to obtain a second target video image.

If the material object includes a moving material object, the moving material object is directly superimposed on the second recognition object image and the specified position of the background image in the motion state of the moving material object to obtain a second target video image.

When the material objects include moving material objects and fixed material objects, the moving material objects are directly superimposed at specified positions on the second recognition object image and the background image in a motion state of the moving material objects, and the fixed material objects are superimposed on the second recognition object image and the background image in a preset display state to obtain a second target video image.

To enhance interaction interest, the embodiment of the present disclosure further provides another image processing method, which will be described below with reference to FIG. 2.

In some embodiments of the present disclosure, the image processing method may be performed by an electronic device. The electronic device may include a device having a communication function, such as a mobile phone, a tablet, a desktop computer, a laptop, an in-vehicle terminal, a wearable electronic device, a multifunction printer, or a smart home device, or may be a device simulated by a virtual machine or a simulator.

Figure 2 shows a schematic flowchart of another image processing method according to an embodiment of the present disclosure.

As shown in FIG. 2, the image processing method includes steps S210 to S250.

Step S210: Detect the object pose of the first recognition object in the initial video image.

In an embodiment of the present disclosure, after acquiring an initial video image, the electronic device can detect an object pose of a first recognition object in the initial video image based on an object detection method.

The initial video image has already been described in S110 in FIG. 1 and will not be discussed here in detail.

Step S220: If the object pose of the first recognition object is the target pose, the motion state of the first recognition object is identified in the initial video image.

In an embodiment of the present disclosure, the electronic device can first determine an object pose of a first recognition object, and if the object pose of the first recognition object is a target pose, identify a motion state of the first recognition object in an initial video image; otherwise, do not process the initial video image.

In the embodiment of the present disclosure, the target posture may be preset according to actual needs and is not limited thereto. For example, the target object may be a hand, and the target posture may be a palm-open posture.

The specific method for identifying the movement state of the first recognition object is similar to S110 shown in Figure 1, and will not be described in detail here.

S230: Identify the movement state of the material object based on the movement state of the first recognition object.

In an embodiment of the present disclosure, after identifying the motion state of the material object, the electronic device can further determine the motion state of the material object, and if the motion state of the material object belongs to the first state, executes step S240, and if the motion state of the material object belongs to the second state, executes step S250.

Step S240: If the motion state of the material object belongs to the first state, the material object and the first style video image are combined according to the motion state of the material object to obtain a first target video image.

Step S250: if the motion state of the material object belongs to the second state, the material object and the second style video image are combined according to the motion state of the material object to obtain a second target video image.

The first style video image and the second style video image may be different stylized images obtained based on the initial video image.

Steps S230 to S250 are similar to steps S120 to S140 shown in Figure 1, and will not be described here in detail.

As a result, in an embodiment of the present disclosure, the initial video image can be edited on the assumption that the first recognition object is in a specified pose, further increasing the interest of the interaction.

To improve the efficiency of material editing, an embodiment of the present disclosure further provides another image processing method, which is described below with reference to FIG. 3.

In some embodiments of the present disclosure, the image processing method may be performed by an electronic device. The electronic device may include a device having a communication function, such as a mobile phone, a tablet, a desktop computer, a laptop, an in-vehicle terminal, a wearable electronic device, a multifunction printer, or a smart home device, or may be a device simulated by a virtual machine or a simulator.

Figure 3 shows a schematic flowchart of yet another image processing method according to an embodiment of the present disclosure.

As shown in FIG. 3, the image processing method includes steps S310 to S350.

Step S310: Identify the motion state of the first recognition object in the initial video image.

Step S310 is similar to S110 shown in Figure 1 and will not be described further here.

Step S320: In the template video of the material object, a target template video image corresponding to the motion state of the first recognition object is selected.

In an embodiment of the present disclosure, after identifying the motion state of the first recognition object, the electronic device can select a target template video image corresponding to the motion state of the first recognition object from a plurality of template video images of the template video of the material object.

Optionally, step S320 may specifically include steps S321 to S323.
Step S321: Identify a target jump frame number corresponding to the motion state of a first recognition object.

In some embodiments, if the motion state of the first recognition object is zero, the target jump frame number is 0, and if the motion state of the first recognition object is not zero, the target jump frame number is 1.

In some other embodiments, the electronic device can pre-set a correspondence between the motion state and the jump frame number, where the jump frame number can be proportional to the motion state, and identify a target jump frame number corresponding to the motion state of the first recognition object based on the correspondence.

Step S322: Identify a target video frame number corresponding to the motion state of the first recognition object based on the target jump frame number.

If the initial video image is the first frame video image, the initial video frame number may be frame 0.

If the initial video image is a non-first frame video image, the initial video frame number may be a video frame number corresponding to a previous reference video image adjacent to the initial video image.

Furthermore, the electronic device can identify a target video frame number corresponding to the motion state of the first recognition object based on the initial video frame number, the motion direction of the first recognition object, i.e., the direction of change of the display parameter variable of the first recognition object, and the target jump frame number.

If the display parameter variable of the first recognition object is a positive number, the electronic device can add the initial video frame number and the target jump frame number to obtain the target video frame number, and if the display parameter variable of the first recognition object is a negative number, the electronic device can subtract the target jump frame number from the initial video frame number to obtain the target video frame number.

Furthermore, if the target jump frame number is a negative number, we stop processing the initial video image.

In step S323, the template video image corresponding to the target video frame number in the template video of the material object is set as the target template video image.

As a result, in an embodiment of the present disclosure, a target template video image corresponding to the motion state of the first recognition object can be quickly and reliably selected.

Step S330: The movement state of the material object in the target template video image is set as the movement state of the material object.

In the embodiment of the present disclosure, one template video image includes a material object having one kind of motion state, that is, the motion states of the material objects in different template video images are different, and the motion states of the material objects in each template video image may be preset according to actual needs.

Therefore, a specific method for identifying the motion state of a material object based on the motion state of the first recognition object may be a method in which the motion state of the material object in the target template video image is taken as the motion state of the material object.

Optionally, step S330 specifically includes:
The step of setting the motion state of the material object at the target video frame number as the motion state of the material object may also be included.

Since one template video image includes a material object having one type of motion state, a video frame number corresponding to one template video image may be used to indicate one type of motion state of the material object, i.e., a video frame number corresponding to one template video image may be used to indicate the motion state of the material object in the corresponding template video image, so that the electronic device can set the motion state of the material object at the target video frame number as the motion state of the material object.

In an embodiment of the present disclosure, after identifying the motion state of the material object, the electronic device can further determine the motion state of the material object, and if the motion state of the material object belongs to a first state, executes step S340, and if the motion state of the material object belongs to a second state, executes step S350.

Optionally, the electronic device can determine whether the motion state of the material object belongs to the first state or the second state by determining a frame number range to which the target video frame number belongs.

The video frame numbers corresponding to one template video image may be used to indicate the motion state of the material object in the corresponding template video image, so that a first frame number range of the template video image pair including the material object in a motion state belonging to a first state, and a second frame number range of the template video image pair including the material object in a motion state belonging to a second state can be identified.

Specifically, the electronic device determines the frame number range to which the target video frame number belongs, and if it determines that the target video frame number belongs to a first frame number range, it determines that the movement state of the material object belongs to a first state, and if it determines that the target video frame number belongs to a second frame number range, it determines that the movement state of the material object belongs to a second state.

Step S340: If the motion state of the material object belongs to the first state, the material object and the first style video image are combined according to the motion state of the material object to obtain a first target video image.

Step S350: if the motion state of the material object belongs to the second state, the material object and the second style video image are combined according to the motion state of the material object to obtain a second target video image.

The first style video image and the second style video image may be different stylized images obtained based on the initial video image.

Steps S340 to S350 are similar to steps S130 to S140 shown in Figure 1, so they will not be explained here in detail.

As a result, in an embodiment of the present disclosure, it is possible to directly determine whether the motion state of a material object belongs to the first state or the second state using the video frame number, eliminating the need to detect the motion state of the material object, reducing the amount of data processing and further improving the efficiency of material editing.

To more clearly explain the image processing method according to the embodiment of the present disclosure, the image processing process according to the embodiment of the present disclosure will be described in detail below using an example in which the template video of the material object is a greeting card falling animation template video, the material object is a greeting card, and the greeting card includes a movable greeting card frame special effect and an immovable greeting card bottom frame special effect.

Figure 4 shows a schematic flow chart of the image processing process according to an embodiment of the present disclosure.

As shown in FIG. 4, the image processing process may include steps S401 to S413.

In step S401, an effect video of a greeting card falling over is played on the shooting preview screen, and effect control guidance information is displayed in each effect video image of each frame in the effect video, and the effect control guidance information may be used to guide the user to open their hand and push their palm back and forth.

In the process of playing the greeting card falling video effect video, if the greeting card frame special effect is the foreground of a person, the electronic device obtains a cartoon style video image corresponding to the image shot in real time, and sequentially superimposes the greeting card bottom frame special effect, the greeting card frame special effect, and the cartoon style video image from the top layer to the bottom layer to obtain an effect video image; if the greeting card frame special effect is the background of a person, the electronic device divides the image shot in real time into a portrait and a background image, and sequentially superimposes the greeting card bottom frame special effect, the portrait, the greeting card frame special effect, and the background image from the top layer to the bottom layer to obtain an effect video image.

After the effect video has completed playing, subsequent steps can be performed from step S402 for real-time collected images of each frame until the electronic device stops collecting images.

Step S402: In the real-time collected image, it is detected whether the user has opened their hand, and if not, step S403 is executed, and if so, step S404 is executed.

The electronic device can detect the user's hand posture in the real-time collected image, and if the hand posture is an open palm posture, executes step S404, otherwise executes step S403.

In step S403, the real-time collected image is displayed on the shooting preview screen, and the process returns to step S402.

In step S404, it is determined whether the user has opened their hand in the collected image of the frame before the real-time collected image, and if not, step S405 is executed, and if so, step S406 is executed.

The electronic device obtains the detection result of the collected image of the previous frame with respect to the hand posture, and based on the detection result, it can determine whether the user's hand is in an open palm posture in the collected image of the previous frame.

Step S405: Identify a template video image of the first frame in the template video of the greeting card falling animation that corresponds to the real-time collected image, and then execute S408.

In step S406, the hand size in the real-time collected image is compared with the hand size in the collected image of the previous frame to calculate the amount of change in hand size, and then step S407 is executed.

In step S407, a template video image corresponding to the real-time collected image is identified based on the amount of hand size change, the positive/negative direction of the amount of hand size change, and the video frame number corresponding to the collected image of the previous frame, and then S408 is executed.

If the hand size change amount is a positive number, it means that the hand is pushed forward, and the electronic device obtains a target jump frame number corresponding to the hand size change amount, and then adds the target jump frame number to the video frame number corresponding to the collected image of the previous frame to identify the playback frame number of the template video of the greeting card falling video, so that the greeting card frame special effect can obtain the effect of the greeting card frame falling backward with respect to the collected image of the previous frame; if not, the electronic device subtracts the target jump frame number from the video frame number corresponding to the collected image of the previous frame to identify the playback frame number of the template video of the greeting card falling video, so that the greeting card frame special effect can obtain the effect of the greeting card frame rising forward with respect to the collected image of the previous frame.

In step S408, it is determined whether the playback frame number of the template video of the greeting card falling video is higher than the frame number threshold, and if so, executes S409; if not, executes S411.

In step S409, image segmentation is performed on the real-time collected image, the portrait and background images in the real-time collected image are obtained, and then step S410 is executed.

Step S410, sequentially superimpose the greeting card bottom frame special effect, the portrait, the greeting card frame special effect, and the background image according to the order from the top layer to the bottom layer to obtain a composite video image, and then execute step S413.

Step S411: perform cartoon stylization processing on the real-time collected image to obtain a cartoon-style video image, and then execute step S412.

Step S412: sequentially superimpose the greeting card bottom frame special effect, the greeting card frame special effect, and the cartoon style video image to obtain a composite video image, and then execute step S413.

Step S413: Display the composite video image on the shooting preview screen.

As a result, the image processing process shown in FIG. 4 can realize the visual display of the effect of a greeting card falling or standing up through a user's face during the process of shooting a video in real time, and can also realize switching between a cartoon effect and a real-life character effect during the process of the greeting card falling or standing up. This makes it possible to automatically generate a hobby video with special effects without the user having to edit the shot video material, thereby increasing the interaction interest and improving the user experience.

An embodiment of the present disclosure further provides an image processing device capable of implementing the above image processing method. Below, an image processing device according to an embodiment of the present disclosure is described with reference to FIG. 5.

In some embodiments of the present disclosure, the image processing device may be an electronic device. The electronic device may include a device having a communication function, such as a mobile phone, a tablet, a desktop computer, a laptop, an in-vehicle terminal, a wearable electronic device, a multifunction printer, or a smart home device, or may be a device simulated by a virtual machine or a simulator.

Figure 5 shows a schematic diagram of the configuration of an image processing device according to an embodiment of the present disclosure.

As shown in FIG. 5, the image processing device 500 may include a first processing unit 510, a second processing unit 520, a first synthesis unit 530, and a second synthesis unit 540.

The first processing unit 510 may be arranged to identify a motion state of a first recognition object in an initial video image.

The second processing unit 520 may be configured to determine the movement state of the material object based on the movement state of the first recognition object.

The first synthesis unit 530 may be configured to synthesize the material object with the first style video image according to the motion state of the material object to obtain a first target video image when the motion state of the material object belongs to a first state.

The second synthesis unit 540 may be arranged to synthesize the material object with the second style video image according to the motion state of the material object to obtain a second target video image when the motion state of the material object belongs to the second state.

The first style video image and the second style video image may be different stylized images obtained based on the initial video image.

In an embodiment of the present disclosure, in an initial video image, a motion state of a first recognition object is identified, a motion state of a material object is identified based on the motion state of the first recognition object, and the motion state of the material object is determined. If the motion state of the material object belongs to the first state, the material object and a first style video image are composited based on the motion state of the material object to obtain a first target video image. If the motion state of the material object belongs to the second state, the material object and a second style video image are composited according to the motion state of the material object to obtain a second target video image. Therefore, material editing can be automatically performed on the initial video image as a video material to obtain an edited composite image, and the user does not need to manually edit the material. This can reduce the time cost of video creation, improve the quality of the video work, and improve the user's experience.

In some embodiments of the present disclosure, the first state can represent a first positional relationship between the material object and the second recognition object in the initial video image, and the second state can represent a second positional relationship between the material object and the second recognition object in the initial video image.

In some embodiments of the present disclosure, the first positional relationship may specifically be that the material object is located in the foreground of the second recognition object, and the second positional relationship may specifically be that the material object is located in the background of the second recognition object.

In some embodiments of the present disclosure, the first style video image may be an image of an initial video image that has been subjected to a style transition process, and the second style video image may be the initial video image.

In some embodiments of the present disclosure, the motion state of the first recognition object is:
A moving state of the first recognition object along the target moving direction;
A posture change state of the first recognition object to the posture of the target object;
and a rotation state along the target rotation direction of the first recognition object.

In some embodiments of the present disclosure, the first processing unit 510 may include a first sub-processing unit and a second sub-processing unit.

The first sub-processing unit may be arranged to detect display parameter variables of a first recognition object in an initial video image.

The second sub-processing unit may be arranged to determine a motion state of the first recognition object based on the display parameter variable.

In some embodiments of the present disclosure, the image processing device 500 may further include a third processing unit, which may be configured to detect an object pose of the first recognition object in the initial video image.

Correspondingly, the first processing unit 510 may be further arranged to determine a motion state of the first recognition object in the initial video image when the object pose of the first recognition object is the target pose.

In some embodiments of the present disclosure, the image processing device 500 may further include a fourth processing unit, which may be configured to select a target template video image in the template video of the material object that corresponds to a motion state of the first recognition object.

Correspondingly, the second processing unit 520 may be further configured to set the motion state of the material object in the target template video image to the motion state of the material object.

In some embodiments of the present disclosure, the fourth processing unit may include a third sub-processing unit, a fourth sub-processing unit, and a fifth sub-processing unit.

The third sub-processing unit may be configured to determine a target jump frame number corresponding to a motion state of the first recognition object.

The fourth sub-processing unit may be configured to identify a target video frame number corresponding to a motion state of the first recognition object based on the target jump frame number.

The fifth sub-processing unit may be configured to set a template video image corresponding to a target video frame number in the template video of the material object as the target template video image.

In some embodiments of the present disclosure, the second processing unit 520 may be further configured to set the motion state of the material object at the target video frame number as the motion state of the material object.

In some embodiments of the present disclosure, the material objects include moving material objects and fixed material objects, and the motion state of the material objects is the motion state of the moving material objects.

Note that the image processing device 500 shown in FIG. 5 can execute each step of the method embodiment shown in FIG. 1 to FIG. 4 and realize each process and effect of the method embodiment shown in FIG. 1 to FIG. 4, and will not be described in detail here.

An embodiment of the present disclosure further provides an image processing device, which may include a processor and a memory, and the memory may be used to store executable instructions. The processor may be used to read and execute the executable instructions from the memory to implement the image processing method in the above embodiment.

FIG. 6 shows a schematic diagram of an image processing device according to an embodiment of the present disclosure. Referring specifically to FIG. 6 below, a schematic diagram suitable for realizing an image processing device 600 according to an embodiment of the present disclosure is shown.

The image processing device 600 in the embodiment of the present disclosure may be an electronic device. The electronic device may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), in-car terminals (e.g., in-car navigation terminals), and wearable devices, and fixed terminals such as digital TVs, desktop computers, and smart home devices.

Note that the image processing device 600 shown in FIG. 6 is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present disclosure.

6, the image processing device 600 may include a processing unit (e.g., a central processing unit, a graphics processor, etc.) 601 capable of performing various suitable operations and processes according to a program stored in a read-only memory (ROM) 602 or loaded from a storage device 608 into a random access memory (RAM) 603. The RAM 603 further stores various programs and data necessary for the operation of the image processing device 600. The processing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to the bus 604.

Typically, the I/O interface 605 can be connected to input devices 606, including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyro, etc., output devices 607, including, for example, a liquid crystal display (LCD), speaker, vibrator, etc., storage devices 608, including, for example, a magnetic tape, hard disk, etc., and communication devices 609. The communication devices 609 enable the image processing device 600 to communicate wirelessly or wired with other devices to exchange data. Although FIG. 6 shows the image processing device 600 having various devices, it should be understood that it is not required to implement or include all of the devices shown. Instead, more or fewer devices may be implemented or included.

An embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored therein, the computer program causing the processor to realize the image processing method of the above embodiment when executed by the processor.

In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowcharts can be implemented as a computer software program.

An embodiment of the present disclosure further provides a computer program product, which may include a computer program that, when executed by a processor, causes the processor to implement the image processing method in the above embodiment.

For example, embodiments of the present application include a computer program product including a computer program carried on a non-transitory computer readable medium, the computer program including program code for performing the method illustrated in the flowchart. In such embodiments, the computer program may be downloaded and installed from a network via a communication device 609, or may be installed from a storage device 608, or may be installed from a ROM 602. When the computer program is executed by the processing device 601, it performs the functions defined in the image processing method of the embodiments of the present application.

It should be noted that the computer-readable medium described in the embodiments of the present disclosure may be a computer-readable signal medium, or a computer-readable storage medium, or any combination of the above. The computer-readable storage medium may be, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in combination with an instruction execution system, apparatus, or device. In embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, the data signal carrying computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may be any computer-readable medium, except for computer-readable storage media, that may transmit, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted by any suitable medium, including, but not limited to, electrical wires, fiber optic cables, RF (radio frequency), or the like, or any suitable combination of the above.

In some embodiments, clients and servers may communicate using any network protocol now known or later developed, such as HTTP, and may be interconnected with any form or medium of digital data communication (e.g., a communications network). Examples of communications networks include local networks ("LANs"), wide area networks ("WANs"), the World Wide Web (e.g., the Internet), end-to-end networks (e.g., ad-hoc end-to-end networks), and other networks now known or later developed.

The computer-readable medium may be included in the image processing device, or may be separate from the image processing device.

The computer-readable medium carries one or more programs, and when the one or more programs are executed by the image processing device, the image processing device is
The video processing system executes the steps of: determining a motion state of a first recognition object in an initial video image; determining a motion state of a material object based on the motion state of the first recognition object; if the motion state of the material object belongs to the first state, combining the material object with a first style video image according to the motion state of the material object to obtain a first target video image; and if the motion state of the material object belongs to the second state, combining the material object with a second style video image according to the motion state of the material object to obtain a second target video image, where the first style video image and the second style video image are different stylized images obtained based on the initial video image.

In embodiments of the present disclosure, computer program code for carrying out the operations of the present disclosure can be written in one or more programming languages or combinations thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and further including, but not limited to, traditional procedural programming languages such as "C" or similar programming languages. The program code can run completely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. When a remote computer is involved, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or wide area network (WAN), or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

The flowcharts and block diagrams in the drawings illustrate system architectures, functions, and operations that can be realized according to the systems, methods, and computer program products of various embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, program segment, or part of code, which includes one or more executable instructions for implementing a certain logical function. It should be noted that in some alternative implementations, the functions shown in the blocks may occur according to an order different from the order shown in the figures. For example, two blocks shown in succession may actually be executed essentially in parallel, or in some cases, according to the reverse order, depending on the functions involved. Also, each block in the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts may be realized in a dedicated system by hardware, or in a combination of dedicated hardware and computer instructions, for performing a certain function or operation.

The units described in the embodiments of the present disclosure may be implemented in a software or hardware manner. The names of the units, if any, do not constitute limitations on the units themselves.

The functionality described herein above may be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that may be utilized include, but are not limited to, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

In this disclosure, a machine-readable medium may be a tangible medium that contains or stores a program that may be used by or in combination with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium includes, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the above. More specific examples of machine-readable storage media include an electrical connection by one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact magnetic disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

The above description is merely a description of the preferred embodiment and the technical principles applied in the present disclosure. As can be understood by those skilled in the art, the scope of the present disclosure is not limited to the technical solution formed by the specific combination of the above technical features, but also includes other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept, for example, a technical solution formed by replacing the above features with technical features having similar functions disclosed in the present disclosure (but not limited thereto).

In addition, although operations have been described employing a particular order, this should not be construed as requiring that these operations be performed in the particular order or sequence shown. In certain circumstances, multitasking and parallel processing may be advantageous. Similarly, the above discussion includes some specific implementation details, but these should not be construed as limitations on the scope of the disclosure. Some features that are described in the context of a single embodiment may also be implemented in a single embodiment in combination. Conversely, various features that are described in the context of a single embodiment may also be implemented in multiple embodiments separately or in any suitable subcombination.

Although the subject matter has been described in language specific to configuration features and/or logical operations of methods, it should be understood that the subject matter defined in the appended claims is not limited to the specific features or operations described above. Rather, the specific features and operations described above are merely example forms for implementing the claims.

Claims (15)

1. An image processing method, comprising:
identifying a motion state of a first recognition object in an initial video image;
determining a motion state of a material object based on a motion state of the first recognition object;
if the motion state of the material object belongs to a first state, synthesizing the material object with a first style video image according to the motion state of the material object to obtain a first target video image;
if the motion state of the material object belongs to a second state, synthesizing the material object with a second style video image according to the motion state of the material object to obtain a second target video image;
the first style video image and the second style video image are different stylized images obtained based on the initial video image.
A method comprising: The first state represents that the material object and a second recognition object in the initial video image satisfy a first positional relationship, and the second state represents that the material object and a second recognition object in the initial video image satisfy a second positional relationship.
2. The method of claim 1 . The first positional relationship is specifically that the material object is located in the foreground of the second recognition object, and the second positional relationship is specifically that the material object is located in the background of the second recognition object.
3. The method of claim 2 . The first style video image is an image obtained by performing style transition processing on the initial video image, and the second style video image is the initial video image.
2. The method of claim 1 . The motion state of the first recognition object is
A moving state of the first recognition object along a target moving direction;
A posture change state of the first recognition object to a posture of a target object;
and a rotation state along a target rotation direction of the first recognition object.
2. The method of claim 1 . The step of identifying a motion state of a first recognition object in an initial video image includes:
detecting a display parameter variable of the first recognition object in the initial video image;
determining a motion state of the first recognition object based on the display parameter variable;
2. The method of claim 1 . Prior to the step of identifying a motion state of a first recognition object in an initial video image, the method further comprises:
detecting an object pose of the first recognition object in the initial video image;
The step of identifying a motion state of a first recognition object in an initial video image includes:
determining a motion state of the first recognition object in the initial video image when an object pose of the first recognition object is a target pose;
2. The method of claim 1 . Prior to the step of identifying a motion state of a material object based on a motion state of the first recognition object, the method further includes:
selecting a target template video image corresponding to a motion state of the first recognition object in a template video of a material object;
The step of identifying a motion state of a material object based on a motion state of the first recognition object includes:
a step of determining a motion state of the material object in the target template video image as a motion state of the material object;
2. The method of claim 1 . The step of selecting a target template video image corresponding to a motion state of the first recognition object in a template video of a material object includes:
determining a target jump frame number corresponding to a motion state of the first recognition object;
determining a target video frame number corresponding to a motion state of the first recognition object according to the target jump frame number;
a step of setting a template video image corresponding to the target video frame number in a template video of the material object as the target template video image;
9. The method of claim 8. The step of setting the motion state of the material object in the target template video image as the motion state of the material object includes:
a step of setting a motion state of the material object at the target video frame number as a motion state of the material object;
10. The method of claim 9. The material objects include moving material objects and fixed material objects, and the motion state of the material objects is the motion state of the moving material objects.
2. The method of claim 1 . An image processing device,
a first processing unit arranged to identify a motion state of a first recognition object in an initial video image;
a second processing unit arranged to determine a motion state of a material object based on a motion state of the first recognition object;
a first synthesis unit, configured to synthesize the material object and a first style video image according to a motion state of the material object to obtain a first target video image when the motion state of the material object belongs to a first state;
a second synthesis unit, configured to synthesize the material object with a second style video image according to the motion state of the material object to obtain a second target video image when the motion state of the material object belongs to a second state;
Including,
the first style video image and the second style video image are different stylized images obtained based on the initial video image.
An apparatus comprising: 1. An image processing device, comprising:
A processor;
a memory for storing executable instructions;
Including,
The processor is adapted to read and execute the executable instructions from the memory to implement the image processing method according to any one of claims 1 to 11.
1. An image processing device comprising: A computer-readable storage medium having a computer program stored thereon,
The computer program, when executed by a processor, causes the processor to implement the image processing method according to any one of claims 1 to 11.
A computer-readable storage medium comprising: A computer program causing a computer to execute the image processing method according to any one of claims 1 to 11.

Images